Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: IMSE: interaction information attention and molecular structure based drug drug interaction extraction

Fig. 2

Architecture of the proposed model. Our model is mainly distributed in four parts. First, BioBERT is used to encode the input sentences, and meanwhile, molecular graph neural network is used to encode the drug structure. Then, Interaction attention vector and Entities attention vector are respectively generated to combine the output of Biobert. Finally, all the obtained information is sent to the classifier for prediction

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us